Answers are grounded in this paper and cite their sources.
We present a theoretical framework for object-based segmentation of color images that extracts the uniformly colored regions on an arbitrary surface all the points of which are exposed to the same set of light sources. This segmentation is a necessary stage before shape-from-shading processing. We introduce a consistent definition of rank and provide a complete classification of interactions among shape, surface color, and illumination. The proposed theory is an extension of known approaches.
No takes yet. Share an insight, caveat, or question.
Петров et al. (1994) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: